Advances in Electric Vehicle Technology: Fault Diagnosis Method Proposed

Strategic Insights -

A new research study has been conducted on electric vehicles, aiming to improve the accuracy of fault diagnosis in permanent magnet synchronous motors. The study proposes a method combining wavelet packet transform (WPT) energy feature extraction and a genetic algorithm-optimized back propagation (BP) neural network. This method has demonstrated high diagnostic accuracy and practical application value, particularly in diagnosing normal operation, inverter open-circuit, and demagnetization faults, with an accuracy rate of 100%.

Key Takeaways:

  • The research proposes a fault diagnosis method for permanent magnet synchronous motors, combining wavelet packet transform (WPT) energy feature extraction and a genetic algorithm-optimized back propagation (BP) neural network.
  • The method demonstrates high diagnostic accuracy, outperforming the SSA-PNN diagnostic model in terms of fault classification accuracy.
  • The proposed method is particularly effective in diagnosing normal operation, inverter open-circuit, and demagnetization faults, with an accuracy rate of 100%.
  • The research was conducted by a team of researchers from Chongqing University of Technology, led by Ming Ye.
  • The study was supported by the Science and Technology Innovation Key R&,D Program of Chongqing.
  • The research has contributed to the advancement of electric vehicle technology, enabling more accurate fault diagnosis and potentially improving vehicle safety and reliability.

Statistics:

  • The proposed method achieved an accuracy rate of 100% in diagnosing normal operation, inverter open-circuit, and demagnetization faults.
  • The method outperformed the SSA-PNN diagnostic model in terms of fault classification accuracy.
  • The research was supported by the Science and Technology Innovation Key R&,D Program of Chongqing.
  • The study was published in the World Electric Vehicle Journal, volume 16, issue 4, page 238.
  • The journal article is available for free at https://doiorg.sdpl.idm.oclc.org/10.3390/wevj16040238.

Sources:

  • NewsRx. Chongqing University of Technology Researchers Update Current Data on Electric Vehicles (Fault Diagnosis of Permanent Magnet Synchronous Motor Based on Wavelet Packet Transform and Genetic Algorithm-Optimized Back Propagation Neural Network). Life Science Weekly. May 13, 2025; p 723.
  • World Electric Vehicle Journal, 2025, 16(4):238. (World Electric Vehicle Journal - http://www.mdpi.com/journal/wevj).
  • MDPI AG (publisher for World Electric Vehicle Journal).
  • Chongqing University of Technology. College of Vehicle Engineering. Chongqing 400054, People's Republic of China.